You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
32 lines
1.2 KiB
32 lines
1.2 KiB
4 years ago
|
from lxml import etree
|
||
|
|
import requests
|
||
|
|
import csv
|
||
|
|
|
||
|
|
fp = open('C://Users/123/Desktop/doubanbook.csv','wt',newline='',encoding='utf-8')
|
||
|
|
writer = csv.writer(fp)
|
||
|
|
writer.writerow(('name', 'url', 'author', 'publisher', 'date', 'price', 'rate', 'comment'))
|
||
|
|
|
||
|
|
urls = ['https://book.douban.com/top250?start={}'.format(str(i)) for i in range(0,250,25)]
|
||
|
|
|
||
|
|
headers = {
|
||
|
|
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
|
||
|
|
}
|
||
|
|
|
||
|
|
for url in urls:
|
||
|
|
html = requests.get(url,headers=headers)
|
||
|
|
selector = etree.HTML(html.text)
|
||
|
|
infos = selector.xpath('//tr[@class="item"]')
|
||
|
|
for info in infos:
|
||
|
|
name = info.xpath('td/div/a/@title')[0]
|
||
|
|
url = info.xpath('td/div/a/@href')[0]
|
||
|
|
book_infos = info.xpath('td/p/text()')[0]
|
||
|
|
author = book_infos.split('/')[0]
|
||
|
|
date = book_infos.split('/')[-2]
|
||
|
|
price = book_infos.split('/')[-1]
|
||
|
|
rate = info.xpath('td/div/span[2]/text()')[0]
|
||
|
|
comments = info.xpath('td/p/span/text()')
|
||
|
|
comment = comments[0] if len(comments) != 0 else "空"
|
||
|
|
writer.writerow((name,url,author,date,price,rate,comment))
|
||
|
|
|
||
|
|
fp.close()
|